Dynamic expansion of acronyms in audio content

Abstract

Examples of the present disclosure describe systems and methods for dynamically expanding acronyms in audio content. In aspects, a user access of an audio resource may be detected. The audio content of the audio resource may be evaluated to identify acronyms. One or more of the identified acronyms may be evaluated based on a user-specific context of the user and/or a global context associated with the user. Based on the evaluated context(s), expansion candidates and corresponding confidence scores may be determined for each identified acronym. Based on the confidence scores, an expansion candidate may be selected and used to replace the identified acronym when the audio content is consumed by the user.

What is claimed is: 
     
       1. A system comprising:
 a processor; and 
 a memory coupled to the processor, the memory comprising computer executable instructions that, when executed by the processor, performs a method comprising:
 detecting an access of audio content by a user, wherein the access of the audio content causes auditory presentation of the audio content to the user; 
 identifying an acronym in the audio content; 
 searching for the acronym and for a corresponding acronym expansion for the acronym in user-specific content, the user-specific content including a document associated with the user; 
 determining that the acronym is not familiar to the user; 
 generating a first confidence score for the corresponding acronym expansion based on a user-specific context, the user-specific context including at least one of the user's recency of interaction with the document and a user interaction type with respect to the document; 
 comparing the first confidence score to a threshold value; 
 determining that the first confidence score does not meet the threshold value; 
 upon determining that the first confidence score does not meet the threshold value, generating a second confidence score for the corresponding acronym expansion based on a global context; 
 generating a total confidence score for the corresponding acronym expansion by combining the first confidence score with the second confidence score; and 
 based on the total confidence score, dynamically substituting the corresponding acronym expansion for the acronym during the auditory presentation of the audio content. 
 
 
     
     
       2. The system of  claim 1 , wherein identifying the acronym in the audio content comprises applying to the audio content at least one of: a natural language processing (NLP) algorithm or an audio recognition algorithm. 
     
     
       3. The system of  claim 1 , wherein identifying the acronym in the audio content comprises:
 accessing a text version of the audio content; and 
 using text-based search tools to identify the acronym in the text version of the audio content. 
 
     
     
       4. The system of  claim 3 , wherein accessing the text version of the audio content comprises at least one of:
 receiving the text version of the audio content with the audio content; 
 receiving a location of the text version of the audio content along with the audio content; or 
 creating the text version of the audio content from the audio content. 
 
     
     
       5. The system of  claim 1 , wherein the user-specific content comprise at least one of:
 a graph database of the user; 
 a user model of the user; or 
 the document associated with the user. 
 
     
     
       6. The system of  claim 1 , wherein identifying the acronym expansion for the acronym comprises:
 creating the user-specific context for the acronym based on one or more resources associated with the user; and 
 creating the global context for the acronym based on one or more global data sources. 
 
     
     
       7. The system of  claim 6 , wherein the one or more global data sources comprise an acronym list provided by at least one of:
 a search engine; 
 a government entity; or 
 an organization associated with the user. 
 
     
     
       8. The system of  claim 6 , wherein the global context for the acronym is further based on at least one of:
 a location of the user; 
 a profession of the user; or 
 a membership of the user. 
 
     
     
       9. The system of  claim 1 , wherein the first confidence score is generated based on a relationship between the user and one or more resources and the relationship between the user and the one or more resources describes at least one of:
 authorship of the one or more resources; or 
 access information of the one or more resources. 
 
     
     
       10. The system of  claim 1 , wherein generating a first confidence score comprises:
 assigning an acronym expansion score to the acronym expansion in each of one or more resources associated with the user; and 
 combining each acronym expansion score to generate the first confidence score. 
 
     
     
       11. The system of  claim 1 , wherein dynamically substituting the acronym expansion for the acronym comprises:
 comparing the total confidence score to the threshold value, wherein the threshold value is used to determine whether to substitute the acronym expansion for the acronym; and 
 when the total confidence score meets or exceeds threshold value, dynamically substituting the acronym expansion for the acronym. 
 
     
     
       12. The system of  claim 1 , wherein the global context is derived using information associated with a user's geographical location. 
     
     
       13. A method comprising:
 detecting an access of audio content by a user device of a user, wherein the access of the audio content causes auditory presentation of the audio content using a media player of the user device; 
 identifying an acronym in the audio content using an evaluation component accessible to the user device; 
 determining that the acronym is not familiar to the user; 
 upon determining that the acronym is not familiar to the user, identifying an acronym expansion for the acronym in one or more resources associated with the user; 
 generating a first confidence score for the acronym expansion based on a user-specific context, the user-specific context including at least one of the user's recency of interaction with one of the one or more resources and a user interaction type with respect to the one of the one or more resources; 
 comparing the first confidence score to a threshold value; 
 determining that the first confidence score does not meet the threshold value; 
 upon determining that the first confidence score does not meet the threshold value, generating a second confidence score for the acronym expansion based on a global context; 
 generating a total confidence score for the acronym expansion by combining the first confidence score with the second confidence score; and 
 when the total confidence score meets or exceeds the threshold value, substituting the acronym expansion for the acronym during the auditory presentation of the audio content. 
 
     
     
       14. The method of  claim 13 , wherein the audio content comprises at least one of:
 an audio file; 
 a video file; 
 broadcast data; or 
 streaming data. 
 
     
     
       15. The method of  claim 13 , wherein the evaluation component is integrated into the media player of the user device. 
     
     
       16. The method of  claim 13 , wherein the evaluation component is integrated into the user device and is separate from the media player of the user device. 
     
     
       17. The method of  claim 13 , wherein identifying the acronym in the audio content comprises:
 providing the audio content to the evaluation component; and 
 before the auditory presentation of the audio content using the media player, applying NLP algorithm or audio recognition algorithm to at least a portion of the audio content. 
 
     
     
       18. The method of  claim 13 , wherein generating the first confidence score comprises:
 assigning an acronym expansion score to the acronym expansion in each of the one or more resources associated with the user; 
 applying a weighting value to each of the one or more resources associated with the user; and 
 combining one or more of the acronym expansion scores and one or more of the weighting values to generate the first confidence score. 
 
     
     
       19. The method of  claim 13 , wherein dynamically substituting the acronym expansion for the acronym comprises:
 providing, by the evaluation component, to acronym expansion to the media player when the acronym occurs during the auditory presentation of the audio content. 
 
     
     
       20. A system comprising:
 a processor; and 
 memory coupled to the processor, the memory comprising computer executable instructions that, when executed by the processor, performs a method comprising:
 detecting an access of audio content by a user, wherein the access of the audio content causes auditory presentation of the audio content to the user; 
 identifying an acronym in the audio content; 
 determining that the acronym is not familiar to the user; 
 upon determining that the acronym is not familiar to the user, evaluating a user-specific context for the user to identify an acronym expansion for the acronym, wherein the user-specific context is based on one or more resources associated with the user and the user-specific context includes at least one of the user's recency of interaction with one of the one or more resources and a user interaction type with respect to the one of the one or more resources; 
 generating a first confidence score for the acronym expansion based on the user-specific context; 
 comparing the first confidence score to a threshold value; 
 determining that the first confidence score does not meet the threshold value; 
 upon determining that the first confidence score does not meet the threshold value, evaluating a global context to generate a second confidence score, wherein the global context is based on one or more resources of one or more entities associated with the user; 
 generating a total confidence score for the acronym expansion by combining the first confidence score with the second confidence score; and 
 based on the total confidence score, dynamically substituting the acronym expansion for at least one instance of the acronym during the auditory presentation of the audio content. 
 
 
     
     
       21. The system of  claim 20 , wherein the one or more resources of the one or more entities associated with the user comprise one or more lists of acronyms and acronym expansions that are at least one of: popular, known, or recognized.